Recommending content based on user behavior tracking and analysis

• US 10,390,062 B2
• Filed: 11/21/2016
• Issued: 08/20/2019
• Est. Priority Date: 11/21/2016
• Status: Active Grant

• Current Assignee: Roku, Inc.
• Original Assignee: Roku, Inc.
• Inventors: Louboutin, Sylvain Rene Yves
• Primary Examiner(s): Kumar, Pankaj
• Assistant Examiner(s): Boyd, Alexander
• Application Number:
  US15/357,289
• Publication Number:
  US 20180146253A1
• Time in Patent Office: 1,002 Days
• CPC Class Codes: G06F 11/3438 monitoring of user actions tracking the activity of the user H04L67/535
• CPC Class Codes: G06F 11/3476 Data logging G06F11/14, G06F11/2205 take precedence
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/835 Timestamp
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08
• CPC Class Codes: H04N 21/44213 Monitoring of end-user related data arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for grouping users into user clusters based on common behavior patterns, and then recommending content to the users based on their respective membership in the clusters. Some embodiments operate by receiving tracking data for a user, where the tracking data includes content viewing behavior information of the user, and/or user interface (UI) navigation behavior information of the user. A distance between the tracking data and a cluster profile associated with a user cluster is determined. If the distance satisfies a threshold associated with the user cluster, then the user is added to the user cluster. Thereafter, the user'"'"'s view experience is customized based the user'"'"'s membership in the user cluster. For example, content recommendations may be generated for the user based on content previously provided to other users in the user cluster, where such content may or may not have previously been provided to the user.

Claims

1. A system comprising:

at least one processor; and

a memory operatively coupled to the at least one processor, the processor configured to;

cluster a user into one or more groups of users based on both a graph data structure indicating how the user interacted with a menu structure for selecting content and a bitmap data structure indicating how the user interacted with content selected from the menu structure;

receive tracking data for a user comprising;

the graph data structure comprising user interface (UI) navigation behavior information of the user between different icons of the menu structure for selecting content, wherein the tracking data of the graph data structure comprises an indication of over which icon of the menu structure the user hovered without selecting and how long the user hovered;

the bitmap data structure comprises a bit for each of a plurality of segments of the selected content available for viewing, wherein each bit of the bitmap data structure indicates whether the segment was viewed by the user;

determine a distance between the tracking data and a cluster profile associated with a user cluster;

determine the distance satisfies a threshold associated with the user cluster;

add the user to the user cluster, in response to determining the distance satisfies the threshold associated with the user cluster;

generate content recommendations based on content previously displayed to other users in the user cluster; and

cause the content recommendations to be provided to the user.

2. The system of claim 1, wherein the processor is further configured to:

receive additional tracking data for the user;

determine a distance between the additional tracking data and a cluster profile associated with a second user cluster, wherein the user is an existing member of the second user cluster;

determine the distance between the additional tracking data and the cluster profile associated with the second user cluster does not satisfy a threshold associated with the second user cluster; and

remove the user from the second user cluster, in response to determining the distance between the additional tracking data and the cluster profile associated with the second user cluster does not satisfy the threshold associated with the second user cluster.

3. The system of claim 1, wherein the processor is further configured to:

update the cluster profile based on the addition of the user to the user cluster.

4. The system of claim 1, wherein the tracking data comprises content viewing behavior information of the user stored in a tree data structure.

5. The system of claim 1, wherein the graph data structure comprises a plurality of nodes, wherein at least some of the nodes correspond to a welcome page and each node stores one or more of information indicating menu tiles/icons the user hovered over, information indicating how long the user hovered, information indicating whether the user hovered more than once over a tile/icon, information indicating how long the user stayed on the welcome page, and information indicating how often the user scrolled to additional pages of the welcome page.

6. The system of claim 1, wherein the bitmap data structure comprises a separate bitmap for each time a particular segment of the selected content was viewed.

7. The system of claim 1, wherein a group bitmap data structure comprises a separate bitmap for each time a particular segment of the selected content was viewed by a majority of users that comprise the group.

8. A computer implemented method, comprising:

clustering a user into one or more groups of users based on both a graph data structure indicating how the user interacted with a menu structure for selecting content and a bitmap data structure indicating how the user interacted with content selected from the menu structure;

receiving tracking data for a user comprising;

the graph data structure comprising user interface (UI) navigation behavior information of the user between different icons of the menu structure for selecting content, wherein the tracking data of the graph data structure comprises an indication of over which icon of the menu structure the user hovered without selecting and how long the user hovered;

the bitmap data structure comprises a bit for each of a plurality of segments of the selected content available for viewing, wherein each bit of the bitmap data structure indicates whether the segment was viewed by the user;

determining a distance between the tracking data and a cluster profile associated with a user cluster;

determining the distance satisfies a threshold associated with the user cluster;

adding the user to the user cluster, in response to determining the distance satisfies the threshold associated with the user duster;

generating content recommendations based on content previously displayed to other users in the user cluster; and

causing the content recommendations to be provided to the user.

9. The method of claim 8, further comprising:

receiving additional tracking data for the user;

determining a distance between the additional tracking data and a cluster profile associated with a second user duster, wherein the user is an existing member of the second user cluster;

determining the distance between the additional tracking data and the duster profile associated with the second user cluster does not satisfy a threshold associated with the second user cluster; and

removing the user from the second user cluster, in response to determining the distance between the additional tracking data and the cluster profile associated with the second user cluster does not satisfy the threshold associated with the second user duster.

10. The method of claim 8, further comprising:

updating the duster profile based on the addition of the user to the user cluster.

11. The method of claim 8, wherein the tracking data comprises content viewing behavior information of the user stored in a tree data structure.

12. The method of claim 8, wherein the graph data structure comprises a plurality of nodes, wherein at least some of the nodes correspond to a welcome page and each node stores one or more of information indicating menu tiles icons the user hovered over, information indicating how long the user hovered, information indicating whether the user hovered more than once over a tile/icon, information indicating how long the user stayed on the welcome page, and information indicating how often the user scrolled to additional pages of the welcome page.

13. A non-transitory;

tangible computer-readable device having instructions stored thereon that, when executed by at least one computing device, causes the at least one computing device to perform operations comprising;

clustering a user into one or more groups of users based on both a graph data structure indicating how the user interacted with a menu structure for selecting content and a bitmap data structure indicating how the user interacted with content selected from the menu structure;

receiving tracking data for a user comprising;

the graph data structure comprising user interface (UI) navigation behavior information of the user between different icons of the menu structure for selecting content, wherein the tracking data of the graph data structure comprises an indication of over which icon of the menu structure the user hovered without selecting and how long the user hovered;

the bitmap data structure comprises a bit for each of a plurality of segments of the selected content available for viewing, wherein each bit of the bitmap data structure indicates whether the segment was viewed by the user;

determining a distance between the tracking data and a cluster profile associated with a user cluster;

determining the distance satisfies a threshold associated with the user cluster;

adding the user to the user cluster, in response to determining the distance satisfies the threshold associated with the user cluster;

generating content recommendations based on content previously displayed to other users in the user duster; and

causing the content recommendations to be provided to the user.

14. The non-transitory, tangible computer-readable device of claim 13, the operations further comprising:

receiving additional tracking data for the user;

determining a distance between the additional tracking data and a cluster profile associated with a second user cluster, wherein the user is an existing member of the second user cluster;

determining the distance between the additional tracking data and the cluster profile associated with the second user cluster does not satisfy a threshold associated with the second user cluster; and

removing the user from the second user cluster, in response to determining the distance between the additional tracking data and the cluster profile associated with the second user cluster does not satisfy the threshold associated with the second user cluster.

15. The non-transitory, tangible computer-readable device of claim 13, wherein the tracking data comprises content viewing behavior information of the user stored in a tree data structure.

16. The non-transitory, tangible computer-readable device of claim 13, wherein the graph data structure comprises a plurality of nodes, wherein at least some of the nodes correspond to a welcome page and each node stores information indicating menu tiles/icons the user hovered over, information indicating how long the user hovered, information indicating whether the user hovered more than once over a tile/icon, information indicating how long the user stayed on the welcome page, and information indicating how often the user scrolled to additional pages of the welcome page.